A Reinforcement Learning Badminton Environment for Simulating Player Tactics (Student Abstract)

TL;DR

This paper introduces a turn-based badminton simulation environment that enables safe, reproducible testing of player tactics and algorithms, facilitating research and training without the costs of real-time matches.

Contribution

It presents a novel badminton environment with detailed rally simulation, states, actions, and training procedures for research and coaching applications.

Findings

Enables safe, reproducible tactical testing in badminton

Supports evaluation of new algorithms in a simulated environment

Facilitates analysis of player strategies and performance

Abstract

Recent techniques for analyzing sports precisely has stimulated various approaches to improve player performance and fan engagement. However, existing approaches are only able to evaluate offline performance since testing in real-time matches requires exhaustive costs and cannot be replicated. To test in a safe and reproducible simulator, we focus on turn-based sports and introduce a badminton environment by simulating rallies with different angles of view and designing the states, actions, and training procedures. This benefits not only coaches and players by simulating past matches for tactic investigation, but also researchers from rapidly evaluating their novel algorithms.